# Improving Neural Machine Translation with Conditional Sequence Generative Adversarial Nets

arXiv: https://arxiv.org/abs/1703.04887 · HTML: https://mlsanity.com/paper/1703.04887/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Mar 2017.

## Built on by (most cited first, 20 of 20)

- [Neural Machine Translation for Low-Resource Languages: A Survey](https://mlsanity.com/paper/2106.15115/) (2021)
- [Continuous 3D Multi-Channel Sign Language Production via Progressive Transformers and Mixture Density Networks](https://mlsanity.com/paper/2103.06982/) (2021)
- [Can Push-forward Generative Models Fit Multimodal Distributions?](https://mlsanity.com/paper/2206.14476/) (2022)
- [Sequence-Level Training for Non-Autoregressive Neural Machine Translation](https://mlsanity.com/paper/2106.08122/) (2021)
- [Mitigating Metric Bias in Minimum Bayes Risk Decoding](https://mlsanity.com/paper/2411.03524/) (2024)
- [Time-series Transformer Generative Adversarial Networks](https://mlsanity.com/paper/2205.11164/) (2022)
- [Guiding Teacher Forcing with Seer Forcing for Neural Machine Translation](https://mlsanity.com/paper/2106.06751/) (2021)
- [Language Generation with Strictly Proper Scoring Rules](https://mlsanity.com/paper/2405.18906/) (2024)
- [Evidential Softmax for Sparse Multimodal Distributions in Deep Generative Models](https://mlsanity.com/paper/2110.14182/) (2021)
- [Learning State Representations via Retracing in Reinforcement Learning](https://mlsanity.com/paper/2111.12600/) (2021)
- [Cross-lingual alignments of ELMo contextual embeddings](https://mlsanity.com/paper/2106.15986/) (2021)
- [Progressive Adversarial Learning for Bootstrapping: A Case Study on Entity Set Expansion](https://mlsanity.com/paper/2109.12082/) (2021)
- [Adversarial Machine Learning in Text Analysis and Generation](https://mlsanity.com/paper/2101.08675/) (2021)
- [PAEG: Phrase-level Adversarial Example Generation for Neural Machine Translation](https://mlsanity.com/paper/2201.02009/) (2022)
- [Differentiable N-gram Objective on Abstractive Summarization](https://mlsanity.com/paper/2202.04003/) (2022)
- [Improvement in Machine Translation with Generative Adversarial Networks](https://mlsanity.com/paper/2111.15166/) (2021)
- [Towards Robust Online Dialogue Response Generation](https://mlsanity.com/paper/2203.03168/) (2022)
- [Soft Alignment Objectives for Robust Adaptation of Language Generation](https://mlsanity.com/paper/2211.16550/) (2022)
- [High-Quality Data Augmentation for Low-Resource NMT: Combining a Translation Memory, a GAN Generator, and Filtering](https://mlsanity.com/paper/2408.12079/) (2024)
- [Generative-Adversarial Networks for Low-Resource Language Data Augmentation in Machine Translation](https://mlsanity.com/paper/2409.00071/) (2024)

## Abstract (arXiv)

This paper proposes an approach for applying GANs to NMT. We build a conditional sequence generative adversarial net which comprises of two adversarial sub models, a generator and a discriminator. The generator aims to generate sentences which are hard to be discriminated from human-translated sentences (i.e., the golden target sentences), And the discriminator makes efforts to discriminate the machine-generated sentences from human-translated ones. The two sub models play a mini-max game and achieve the win-win situation when they reach a Nash Equilibrium. Additionally, the static sentence-level BLEU is utilized as the reinforced objective for the generator, which biases the generation towards high BLEU points. During training, both the dynamic discriminator and the static BLEU objective are employed to evaluate the generated sentences and feedback the evaluations to guide the learning of the generator. Experimental results show that the proposed model consistently outperforms the traditional RNNSearch and the newly emerged state-of-the-art Transformer on English-German and Chinese-English translation tasks.